Voice identification via radio wave demodulation

Abstract

A system includes a phased antenna array configured to receive signals from at least one signal source not initially designed to provide a signal related to sound. The system also includes a signal processor configured to locate the at least one signal source using the received signals and detect a movement of the at least one signal source relative to the phased antenna array, wherein the detected movement is at least partially in response to sound waves impinging on the at least one signal source. The system further includes a sound demodulator configured to demodulate the sound waves from the detected movement.

What is claimed is: 
     
         1 . A system comprising:
 a phased antenna array configured to receive signals from at least one signal source not initially designed to provide a signal related to sound;   a signal processor configured to locate the at least one signal source using the received signals and detect a movement of the at least one signal source relative to the phased antenna array, wherein the detected movement is at least partially in response to sound waves impinging on the at least one signal source; and   a sound demodulator configured to demodulate a sound signal from the detected movement.   
     
     
         2 . The system of  claim 1 , wherein the at least one signal source includes one or more of a vibration detector, a passive tag, and/or a user device. 
     
     
         3 . The system of  claim 2 , wherein the vibration detector actively transmits the signals to the phased antenna array without being pinged by the phased antenna array. 
     
     
         4 . The system of  claim 2 , wherein the passive tag transmits the signals to the phased antenna array in response to being pinged by the phased antenna array. 
     
     
         5 . The system of  claim 2 , wherein the system operates in an active and/or a passive mode, such that, in the passive mode, radio waves that naturally occur without prompting or responding emanate from the at least one signal source, and, in the active mode, the phased antenna array is configured to transmit radio waves that are reflected or retransmitted by the at least one signal source to create a larger sample of data for sound demodulation. 
     
     
         6 . The system of  claim 1 , wherein the signal processor is configured to locate the at least one signal source using one or more of Kalman filtering, a joint probabilistic data association (JPDA) operation, and/or a Multiple Signal Classification (MUSIC) algorithm. 
     
     
         7 . The system of  claim 1 , wherein the signal processor is configured to triangulate a location of the at least one signal source using an angle of arrival (AoA) calculation based on a difference in phase and time of the received signals arriving at the phased antenna array. 
     
     
         8 . The system of  claim 1 , wherein the signal processor is configured to determine a location of the at least one signal source using trilateration. 
     
     
         9 . The system of  claim 1 , wherein the signal processor is further configured to identify signal components of the signals from the at least one signal source. 
     
     
         10 . The system of  claim 1 , wherein the sound demodulator is configured to filter identified components of the received signals to produce a filtered signal. 
     
     
         11 . The system of  claim 10 , wherein the sound demodulator is configured to process the filtered signal to isolate the sound signal from noise in the filtered signal. 
     
     
         12 . The system of  claim 11 , wherein the sound demodulator is configured to process the filtered signal by one or more of independent component analysis, fast Fourier transform, low-pass filtering, and/or digital signal processing. 
     
     
         13 . The system of  claim 11 , wherein the sound demodulator is configured to apply a sound recognition algorithm to identify the sound signal in the received signals. 
     
     
         14 . The system of  claim 13 , wherein the sound recognition algorithm uses machine learning to identify a particular sound in the sound signal. 
     
     
         15 . The system of  claim 13 , wherein the sound demodulator is configured to generate a voice print from the sound signal if the sound signal contains a voice. 
     
     
         16 . The system of  claim 15 , wherein the voice print is identified based on features including Mel-Frequency Cepstral Coefficients (MFCCs), Linear Predictive Coding (LPC) coefficients, and/or formant frequencies. 
     
     
         17 . The system of  claim 13 , wherein the sound demodulator is further configured to amplify the sound signal to an audible intensity. 
     
     
         18 . The system of  claim 17 , further comprising a sound output device to play the amplified sound signal. 
     
     
         19 . A method comprising:
 receiving, via a phased antenna array, signals from at least one signal source not initially designed to provide a signal related to sound;   locating, via signal processor, the at least one signal source using the received signals;   detecting, via the signal processor, a movement of the at least one signal source relative to the phased antenna array, wherein the detected movement is at least partially in response to sound waves impinging on the at least one signal source; and   demodulating a sound signal from the detected movement.   
     
     
         20 . The method of  claim 19 , further comprising playing the sound signal on an output device.